In the architecture, engineering, and construction industries, the integration of Building Information Modeling (BIM) has become instrumental in shaping the design and commissioning of smart buildings. At the center of this development is the pursuit of more intelligent, efficient, and sustainable built environments. The emergence of smart buildings equipped with advanced sensor networks and automation systems increasingly requires the implementation of Digital Twins (DT) for the direct coupling of BIM methods for integral building planning, commissioning, and operational monitoring. While simulation tools and methods exist in the design phase of developing advanced controls, their mapping to construction or post-construction models is less well developed. Through systematic, keyword-based literature research on publisher-independent databases, this review paper gives a comprehensive overview of the state of the research on BIM integration of building control systems with a primary focus on combined controls for daylight and artificial lighting systems. The review, supported by a bibliometric literature analysis, highlights major development fields in HVAC controls, failure detection, and fire-detection systems, while the integration of daylight and artificial lighting controls in Digital Twins is still at an early stage of development. In addition to already existing reviews in the context of BIM and Digital planning methods, this review particularly intends to build the necessary knowledge base to further motivate research activities to integrate simulation-based control methods in the BIM planning process and to further close the gap between planning, implementation, and commissioning.

A significant proportion of the total energy consumption in office buildings is attributable to lighting. Enhancements in energy efficiency are currently achieved through strategies to reduce artificial lighting by intelligent daylight utilization. Control strategies in the field of daylighting and artificial lighting are mostly rule-based and focus either on comfort aspects or energy objectives. This paper aims to provide an overview of published scientific literature on enhanced control strategies, in which new control approaches are critically analysed regarding the fulfilment of energy efficiency targets and comfort criteria simultaneously. For this purpose, subject-specific review articles from the period between 2015 and 2020 and their research sources from as far back as 1978 are analysed. Results show clearly that building controls increasingly need to address multiple trades to achieve a maximum improvement in user comfort and energy efficiency. User acceptance can be highlighted as a decisive factor in achieving targeted system efficiencies, which are highly determined by the ability of active user interaction in the automatic control system. The future trend is moving towards decentralized control concepts including appropriate occupancy detection and space zoning. Simulation-based controls and learning systems are identified as appropriate methods that can play a decisive role in reducing building energy demand through integral control concepts.

With buildings accounting for 40% of global energy consumption, heating, ventilation, and air conditioning (HVAC) systems represent the single largest opportunity for emissions reduction, consuming up to 60% of commercial building energy while maintaining occupant comfort. This critical balance between energy efficiency and human comfort has traditionally relied on rule-based and model predictive control strategies. Given the multi-objective nature and complexity of modern HVAC systems, these approaches fall short in satisfying both objectives. Recently, reinforcement learning (RL) has emerged as a method capable of learning optimal control policies directly from system interactions without requiring explicit models. However, standard RL approaches frequently violate comfort constraints during exploration, making them unsuitable for real-world deployment where occupant comfort cannot be compromised. This paper addresses two fundamental challenges in HVAC control: the difficulty of constrained optimization in RL and the challenge of defining appropriate comfort constraints across diverse conditions. We adopt a safe RL with a neural barrier certificate framework that (1) transforms the constrained HVAC problem into an unconstrained optimization and (2) constructs these certificates in a data-driven manner using neural networks, adapting to building-specific comfort patterns without manual threshold setting. This approach enables the agent to almost guarantee solutions that improve energy efficiency and ensure defined comfort limits. We validate our approach through seven experiments spanning residential and commercial buildings, from single-zone heat pump control to five-zone variable air volume (VAV) systems. Our safe RL framework achieves energy reduction compared to baseline operation while maintaining higher comfort compliance than unconstrained RL. The data-driven barrier construction discovers building-specific comfort patterns, enabling context-aware optimization impossible with fixed thresholds. While neural approximation prevents absolute safety guarantees, reducing catastrophic safety failures compared to unconstrained RL while maintaining adaptability positions this approach as a developmental bridge between RL theory and real-world building automation, though the considerable gap in both safety and energy performance relative to rule-based control indicates the method requires substantial improvement for practical deployment.